7 Tips To Start Using Speech Analytics In Any Call Center

Posted by Emily Blazensky on Jul 19, 2016 9:41:07 AM


VB Dash Sample

Speech Analytics is a powerful tool to help businesses search, analyze and surface important information from 100% of your business' phone calls. Many contact centers currently use humans to manually listen and score less than 5% of all calls for quality assurance and agent monitoring purposes.With Speech Analytics, a contact center can now automatically score 100% of their calls and go beyond just QA and agent monitoring efforts.

Imagine being able to track your customers wants and needs, their thoughts on competitors, or their favorite products… now you can. VoiceBase's Speech Analytics API allows businesses to define the keywords and phrases they want to track in order to better understand their consumers. With this information, trends can be tracked, up-sell opportunities can be identified, quality assurance measures can be robust and agent monitoring can be completely automated. 

Need some inspiration? Check out these popular posts on Speech Analytics:



There are two methods to detect information in spoken content; keyword spotting and predictive insights.

Keyword spotting is used for specific terms and phrases that a company knows could be said during a call. This method can be applied during an API request and therefore can be done on the fly.

Predictive Insights, on the other hand, is used to detect complex events such as Hot Leads, Pre-Churn Accounts, Appointments Made and more. This is done through machine learning and predictive analytics training processes, which need to be prepared prior to an API request. 

Because Keyword Spotting can be implemented 'on the fly' with any API request, this post will focus on what terms to look for first. If you're interested in learning more about Predictive Insights, you'll like this blog on auto call scoring:


auto call scoring 3 Major Benefits of Auto Call Scoring For Cloud Contact Centers.

Today’s contact center is not lacking for data. There are mountains of calls waiting to be mined for intelligence... [read more]



The most important question to ask when deciding what keywords/phrases to look for first is ‘what do I need to improve first?’ Based on the answer to that question your team can prioritize what elements of your call center should be focused on - customer service, sales, customer retention, etc. 

1. Opinion Statements

  • “I want” “I need” “I like” “I hate” “I wish” (spoken by the customer)
  • These can be used to understand the "Voice of the Customer" and prioritize efforts to maximize customer satisfaction

2. Competitor Names

  • Make sure to also include specific product names from competitors as well (spoken by the customer)
  • By learning what your customers think about competitors and how they compare your brand/company to theirs is important to any business

3. Product & Feature Terms

  • Monitoring your own product and feature terms is important to spot trends and learn which customers favor and which customers dislike

4. Profanity

  • This one is obvious, and should be spotted for both the customer and the agent
  • Businesses can quickly detect angry customers and use this information to improve customer retention
  • It is also important to red flag any agent profanity, and to escalate those calls to management for review

5. Exciting Language

  • “Interested in” (spoken by the customer) “purchase” (spoken by the customer)
  • This list is very broad however detecting when a caller is VERY interested versus KIND OF interested can be useful when looking for up-sell opportunities or identifying a new brand evangelist

6. Required vs. Unauthorized terms

  • Spot mandatory script terms and phrases such as: “money-back guarantee”, “two year commitment” “free trial” “30 day trial” (spoken by the agent)
  • Ex: “No contract needed”, “percent discount”(spoken by the agent)
  • These can be used for script adherence or agent monitoring automation

7. Customer Dissatisfaction

  • Ex: “I’m switching to…” “I’m not happy with” “cancel account” “close account” “cancel service” “stop service” “last bill” “last invoice” (spoken by the customer)
  • Don't stop at learning from these calls, but reach out, offer discounts and try to improve customer retention when a customer has been identified as "upset" "angry" or "dissatisfied" 


Want to get started with speech analytics? Contact us here to set up a free demo of VoiceBase's speech recognition, speech analytics and predictive insights.



Topics: call center, speech analytics

Written by Emily Blazensky

As Director of Marketing for VoiceBase, an API-based and enterprise grade speech analytics platform, Emily has developed unique and successful marketing strategies to meet the needs of an emerging industry leader, with a rapidly growing customer base. Emily has a keen grasp of the strategies to elevate awareness of the multiple ways speech technology can be applied to improve business process automation.
Find me on:

What is Big Voice?

AI-powered speech analytics for the cloud

VoiceBase is defining the future of deep learning and communications by providing unparalleled access to spoken information for businesses to make better decisions. With flexible APIs developers and enterprises build scalable solutions with VoiceBase by embedding speech-to-text, speech analytics, and predictive analytics capabilities into any big voice application. 



The Modern Speech Analytics Playbook

Screenshot 2019-09-25 13.29.39

Subscribe to Email Updates

Recent Posts